Mystery: examining a crime scene

Bad Writing Habits

Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.

Creative Writing Hallucination

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
GPT-5.4 (Reasoning)	92%
GPT-5.4	92%
GPT-5.5	91%
GPT-5.4 (Reasoning, Low)	91%
GPT-5.5 (Reasoning, Low)	90%
GPT-5.5 (Reasoning)	90%
GPT-5.4 Mini	89%
GPT-5.4 Mini (Reasoning)	89%
GPT-5.4 Mini (Reasoning, Low)	87%
Qwen3.6 Max Preview	87%
Qwen 3.6 35B	86%
Qwen 3.6 Flash	86%
Claude Opus 4.7 (Reasoning)	86%
GPT-5	85%
GPT-5.1	85%
Rocinante 12B	85%
MoonshotAI: Kimi K2.6	85%
Claude Sonnet 4.5	85%
Grok 4.3	84%
Qwen 3.5 397B A17B	84%

	Score	Cost	Time
Rocinante 12B	85%	$0.0006	25.4s
Qwen 3.6 35B	86%	$0.0090	58.9s
GPT-5.4 Mini (Reasoning, Low)	87%	$0.016	18.8s
GPT-5.4 Mini	89%	$0.017	19.5s
Qwen 3.6 Flash	86%	$0.0090	36.8s
Grok 4.3	84%	$0.0053	27.4s
Mistral Small 4 (Reasoning)	83%	$0.0022	30.7s
Qwen 3 32B	83%	$0.0012	39.7s
DeepSeek V4 Flash	83%	$0.0005	26.7s
GPT-5.4 Mini (Reasoning)	89%	$0.031	37.4s
GPT-5.4 Nano	80%	$0.0057	20.4s
Mistral Large 3	82%	$0.0026	28.4s
Mistral Small Creative	81%	$0.0006	9.8s
LFM2 24B	78%	$0.0002	33.2s
Mistral NeMO	81%	$0.0003	11.1s
Qwen3 235B A22B Instruct 2507	81%	$0.0011	1.1m
Mistral Small 4	79%	$0.0011	18.0s
GPT-5.4 Nano (Reasoning, Low)	81%	$0.0055	20.4s
Hermes 3 405B	82%	$0.0020	59.2s
DeepSeek V3 (2025-03-24)	80%	$0.0016	33.7s

	Score	Cost	Speed	Stability
GPT-5.4 Mini (Reasoning, Low)	87%	$0.016	18.8s	84%
GPT-5.4 Mini	89%	$0.017	19.5s	80%
GPT-5.4 Mini (Reasoning)	89%	$0.031	37.4s	84%
GPT-5.4	92%	$0.057	1.6m	88%
Qwen 3.6 Flash	86%	$0.0090	36.8s	80%
Qwen 3.6 35B	86%	$0.0090	58.9s	81%
Grok 4.3	84%	$0.0053	27.4s	79%
Qwen 3 32B	83%	$0.0012	39.7s	80%
Rocinante 12B	85%	$0.0006	25.4s	77%
GPT-5.4 (Reasoning, Low)	91%	$0.060	1.6m	87%
Mistral Small 4 (Reasoning)	83%	$0.0022	30.7s	78%
Claude Sonnet 4.5	85%	$0.029	35.7s	81%
Mistral Large 3	82%	$0.0026	28.4s	76%
DeepSeek V4 Flash	83%	$0.0005	26.7s	75%
Mistral Small Creative	81%	$0.0006	9.8s	75%
GPT-5.4 Nano (Reasoning, Low)	81%	$0.0055	20.4s	77%
GPT-5.4 Nano	80%	$0.0057	20.4s	77%
Mistral NeMO	81%	$0.0003	11.1s	75%
Grok 4.20	82%	$0.0078	40.7s	77%
Writer: Palmyra X5	81%	$0.011	24.2s	77%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
29	GPT-5.4 (Reasoning)	$0.100	3.1m	91%	94	93	93	91	91	92%
4	GPT-5.4	$0.057	1.6m	88%	95	92	92	90	89	92%
103	GPT-5.5	$0.166	1.8m	85%	95	90	90	90	88	91%
10	GPT-5.4 (Reasoning, Low)	$0.060	1.6m	87%	93	93	92	89	85	91%
98	GPT-5.5 (Reasoning, Low)	$0.156	2.1m	86%	93	92	90	89	88	90%
108	GPT-5.5 (Reasoning)	$0.164	2.1m	87%	91	91	89	89	88	90%
2	GPT-5.4 Mini	$0.017	19.5s	80%	95	90	87	86	85	89%
3	GPT-5.4 Mini (Reasoning)	$0.031	37.4s	84%	93	89	88	87	86	89%
1	GPT-5.4 Mini (Reasoning, Low)	$0.016	18.8s	84%	89	88	87	87	84	87%
37	Qwen3.6 Max Preview	$0.046	3.4m	85%	89	88	87	86	85	87%
6	Qwen 3.6 35B	$0.0090	58.9s	81%	90	88	88	87	78	86%
5	Qwen 3.6 Flash	$0.0090	36.8s	80%	89	89	86	84	80	86%
31	Claude Opus 4.7 (Reasoning)	$0.071	34.5s	82%	89	86	86	84	83	86%
80	GPT-5	$0.073	3.0m	83%	87	87	86	83	83	85%
39	GPT-5.1	$0.063	1.5m	83%	86	86	85	85	83	85%
9	Rocinante 12B	$0.0006	25.4s	77%	92	89	87	79	76	85%
143	MoonshotAI: Kimi K2.6	$0.043	8.2m	79%	90	86	85	82	81	85%
12	Claude Sonnet 4.5	$0.029	35.7s	81%	87	85	84	84	82	85%
7	Grok 4.3	$0.0053	27.4s	79%	88	87	85	83	79	84%
40	Qwen 3.5 397B A17B	$0.030	2.3m	80%	86	85	85	85	79	84%
11	Mistral Small 4 (Reasoning)	$0.0022	30.7s	78%	87	86	83	82	78	83%
8	Qwen 3 32B	$0.0012	39.7s	80%	85	84	83	83	80	83%
47	Qwen 3.6 27B	$0.016	1.5m	74%	91	82	81	81	80	83%
134	Claude Opus 4	$0.147	1.0m	79%	85	85	84	83	77	83%
50	Claude Opus 4.7	$0.064	34.5s	80%	85	84	84	83	79	83%
35	Grok 4.20 (Beta, Reasoning)	$0.036	33.9s	77%	86	86	83	82	76	83%
14	DeepSeek V4 Flash	$0.0005	26.7s	75%	90	83	82	80	78	83%
13	Mistral Large 3	$0.0026	28.4s	76%	88	82	81	81	80	82%
128	Gemini 3.1 Pro (Preview)	$0.083	1.5m	71%	91	88	80	78	75	82%
27	Hermes 3 405B	$0.0020	59.2s	74%	88	86	82	78	76	82%
51	Grok 4.20 (Reasoning)	$0.016	1.4m	75%	88	86	81	79	76	82%
21	MiniMax M2.5	$0.0030	1.0m	76%	87	83	83	81	75	82%
19	Grok 4.20	$0.0078	40.7s	77%	85	84	81	81	78	82%
45	Claude Sonnet 4.6	$0.031	48.5s	77%	87	83	83	77	77	82%
83	Grok 4.3 (Reasoning)	$0.016	2.6m	73%	87	85	81	78	76	81%
23	Qwen3 235B A22B Instruct 2507	$0.0011	1.1m	77%	85	84	81	79	78	81%
59	Z.AI GLM 5.1	$0.012	1.3m	73%	89	85	82	77	73	81%
24	Qwen 3.5 Flash	$0.0019	36.5s	75%	88	81	80	79	78	81%
43	Mistral Large 2	$0.011	28.7s	72%	89	84	79	78	76	81%
20	Writer: Palmyra X5	$0.011	24.2s	77%	83	83	80	80	79	81%
22	o4 Mini	$0.014	22.3s	77%	83	83	82	79	76	81%
18	Mistral NeMO	$0.0003	11.1s	75%	87	80	80	80	77	81%
15	Mistral Small Creative	$0.0006	9.8s	75%	86	81	80	78	78	81%
123	Claude Opus 4.6 (Reasoning)	$0.086	1.4m	76%	84	84	81	79	76	81%
16	GPT-5.4 Nano (Reasoning, Low)	$0.0055	20.4s	77%	84	81	81	79	77	81%
26	Grok 4.1 Fast	$0.0016	40.6s	75%	84	83	80	79	75	80%
17	GPT-5.4 Nano	$0.0057	20.4s	77%	83	83	82	79	75	80%
56	o4 Mini High	$0.023	38.2s	74%	86	82	80	78	76	80%
68	Qwen 3.5 Plus (2026-04-20)	$0.015	1.5m	74%	85	83	80	79	74	80%
48	Z.AI GLM 5 Turbo	$0.0081	37.9s	72%	87	83	80	77	74	80%
32	GPT-5 Mini	$0.0099	40.3s	76%	84	79	79	79	79	80%
53	Mistral Large	$0.013	35.0s	73%	87	80	80	76	75	80%
112	GPT-5.2	$0.060	1.6m	75%	84	80	79	78	78	80%
34	DeepSeek V3 (2025-03-24)	$0.0016	33.7s	74%	83	83	80	80	72	80%
64	GPT-4.1	$0.018	40.9s	73%	84	83	79	76	75	79%
42	Gemma 3 27B	$0.0007	45.4s	73%	85	83	80	77	73	79%
28	Mistral Small 4	$0.0011	18.0s	75%	84	81	80	78	74	79%
60	DeepSeek V4 Pro (Reasoning)	$0.0035	1.8m	76%	83	81	81	76	75	79%
49	Stealth: Healer Alpha	$0.0000	24.6s	71%	85	84	78	77	72	79%
65	Ministral 3 8B	$0.0023	1.5m	73%	86	81	80	75	75	79%
44	Gemini 3.1 Flash Lite (Preview)	$0.0026	8.1s	71%	86	82	77	76	76	79%
25	Ministral 3 14B	$0.0005	12.5s	75%	82	81	80	79	74	79%
91	Gemini 2.5 Pro	$0.040	41.1s	72%	84	82	78	77	74	79%
33	Mistral Medium 3.1	$0.0045	34.0s	76%	82	81	81	77	74	79%
63	Qwen 3.5 9B	$0.0008	1.2m	72%	85	80	78	75	75	79%
36	DeepSeek V4 Flash (Reasoning)	$0.0008	38.0s	75%	82	82	81	77	73	79%
41	ByteDance Seed 1.6 Flash	$0.0014	30.1s	73%	84	80	78	77	75	79%
52	DeepSeek-V2 Chat	$0.0016	36.9s	72%	84	81	80	79	70	79%
30	Gemma 3 12B	$0.0004	37.1s	76%	81	81	80	76	75	79%
85	Cohere Command R+ (Aug. 2024)	$0.016	1.3m	71%	84	84	79	75	71	79%
96	Grok 4	$0.045	1.7m	77%	80	79	78	78	77	79%
38	GPT-5.4 Nano (Reasoning)	$0.0060	22.2s	75%	82	80	79	77	74	78%
62	Gemini 2.5 Flash (Reasoning)	$0.013	24.5s	72%	83	81	80	79	69	78%
79	Claude 3.5 Sonnet	$0.044	37.5s	75%	81	80	78	77	76	78%
58	Qwen 3.5 122B	$0.013	36.8s	74%	83	81	81	74	72	78%
74	Grok 4.20 (Beta)	$0.015	13.1s	69%	88	78	78	75	72	78%
46	LFM2 24B	$0.0002	33.2s	73%	83	82	81	74	71	78%
89	Claude 3.7 Sonnet	$0.037	46.9s	73%	83	79	79	78	72	78%
121	Claude Opus 4.5	$0.067	56.1s	73%	82	80	77	77	75	78%
114	ByteDance Seed 2.0 Lite	$0.012	2.1m	68%	89	80	79	72	70	78%
66	MiniMax M2.7	$0.0033	1.3m	74%	82	80	78	76	75	78%
125	Claude Opus 4.6	$0.077	1.3m	75%	81	80	78	76	74	78%
70	Z.AI GLM 5	$0.0079	1.1m	73%	83	77	77	77	77	78%
73	GPT-4o, May 13th (temp=0)	$0.028	19.0s	73%	82	80	77	76	74	78%
61	Gemini 3.1 Flash Lite	$0.0026	9.6s	70%	82	82	77	76	70	78%
55	Gemini 2.5 Flash	$0.0057	11.6s	73%	81	78	76	76	74	77%
86	DeepSeek V4 Pro	$0.0044	1.4m	71%	83	79	77	76	71	77%
57	Xiaomi MIMO v2.5	$0.0057	34.4s	74%	79	78	77	77	73	77%
54	Gemini 2.5 Flash Lite	$0.0009	11.8s	72%	80	79	77	76	72	77%
75	Claude 3 Haiku	$0.0020	15.6s	68%	85	77	75	73	72	76%
81	Grok 4 Fast	$0.0016	27.2s	68%	82	82	75	74	69	76%
99	Qwen 3.5 27B	$0.0097	57.2s	69%	84	77	75	73	72	76%
102	Qwen 3.5 35B	$0.011	37.9s	66%	86	77	74	73	72	76%
76	Llama 3.1 Nemotron 70B	$0.0023	32.3s	70%	83	78	76	72	72	76%
138	ByteDance Seed 2.0 Mini	$0.0049	5.4m	75%	77	77	76	76	75	76%
71	Llama 3.1 70B	$0.0007	33.1s	71%	80	78	75	74	74	76%
72	GPT-4o Mini (temp=1)	$0.0011	25.2s	71%	81	75	75	75	74	76%
132	DeepSeek V3.2	$0.0011	3.3m	67%	84	78	75	72	70	76%
69	Gemini 2.5 Flash Lite (Reasoning)	$0.0025	26.5s	72%	79	78	75	74	74	76%
77	Arcee AI: Trinity Large (Preview)	$0.0000	42.7s	70%	80	78	75	73	72	76%
117	MoonshotAI: Kimi K2.5	$0.012	1.0m	66%	86	77	76	70	68	75%
104	GPT-4o, May 13th (temp=1)	$0.030	15.6s	70%	82	76	75	72	71	75%
127	Claude Sonnet 4.6 (Reasoning)	$0.043	1.1m	70%	81	77	77	74	67	75%
118	Hermes 3 70B	$0.0006	31.1s	62%	84	82	71	71	69	75%
120	Z.AI GLM 4.7	$0.0098	1.9m	69%	80	77	74	73	72	75%
131	ByteDance Seed 1.6	$0.016	3.1m	72%	78	75	74	74	74	75%
110	Aion 2.0	$0.0051	1.2m	68%	81	79	74	72	69	75%
67	GPT-4o Mini (temp=0)	$0.0010	24.7s	73%	77	76	75	74	73	75%
78	DeepSeek V3 (2024-12-26)	$0.0017	40.7s	71%	78	77	75	74	70	75%
101	Ministral 3B	$0.0001	1.1m	68%	82	76	73	72	71	75%
93	Ministral 3 3B	$0.0015	55.5s	70%	80	77	75	73	70	75%
82	Qwen 2.5 72B	$0.0006	27.7s	70%	79	79	75	71	71	75%
88	Xiaomi MIMO v2.5 Pro	$0.0080	52.9s	72%	77	76	75	74	71	75%
119	Z.AI GLM 4.7 Flash	$0.0020	1.3m	66%	84	73	73	72	70	75%
94	Z.AI GLM 4.5 Air	$0.0018	34.5s	69%	78	78	75	73	67	74%
133	Gemini 3 Pro (Preview)	$0.049	49.7s	69%	79	78	74	71	69	74%
126	Claude Sonnet 4	$0.028	43.4s	66%	79	79	74	73	65	74%
95	Stealth: Hunter Alpha	$0.0000	46.8s	69%	80	77	76	69	68	74%
109	DeepSeek V3.1	$0.0014	1.7m	70%	78	76	75	71	70	74%
87	GPT-4o, Aug. 6th (temp=0)	$0.016	29.9s	73%	75	74	74	74	73	74%
122	Z.AI GLM 4.6	$0.0062	1.4m	67%	78	77	72	72	70	74%
105	GPT-4o, Aug. 6th (temp=1)	$0.016	36.9s	70%	79	75	75	71	69	74%
90	GPT-4.1 Mini	$0.0027	16.6s	69%	78	76	74	70	70	74%
113	Claude Haiku 4.5	$0.0093	20.2s	66%	80	79	73	69	67	74%
84	Gemma 3 4B	$0.0002	18.9s	70%	76	75	74	72	70	73%
97	WizardLM 2 8x22b	$0.0016	24.6s	69%	78	77	76	69	66	73%
111	Qwen 3.5 Plus (2026-02-15)	$0.0051	25.8s	67%	79	74	72	71	70	73%
140	Llama 3.1 8B	$0.0003	2.0m	63%	82	77	70	69	68	73%
100	Ministral 8B	$0.0002	9.9s	67%	80	77	76	68	63	73%
115	Gemini 3.1 Flash Lite (Reasoning)	$0.0026	22.1s	65%	83	77	77	68	60	73%
116	Z.AI GLM 4.5	$0.0045	37.2s	67%	79	73	73	72	66	73%
92	GPT-4.1 Nano	$0.0006	10.5s	70%	75	74	74	71	68	72%
106	Gemini 3 Flash (Preview)	$0.0067	17.5s	69%	74	72	72	71	68	72%
107	Arcee AI: Trinity Mini	$0.0003	9.0s	67%	77	75	73	68	66	72%
130	Gemma 4 31B (Reasoning)	$0.0012	1.7m	68%	74	74	70	70	70	72%
124	Gemini 3 Flash (Preview, Reasoning)	$0.010	25.1s	66%	78	73	72	68	66	72%
129	Gemma 4 31B	$0.0008	1.5m	67%	74	73	71	69	68	71%
137	Nemotron 3 Super	$0.0000	1.3m	65%	74	70	68	68	67	69%
141	Gemma 4 26B (Reasoning)	$0.0013	2.2m	66%	72	71	69	67	66	69%
139	Gemma 4 26B	$0.0007	41.6s	63%	77	72	71	66	60	69%
146	Mistral Small 3.2 24B	$0.0034	1.8m	62%	77	70	69	68	60	69%
135	Inception Mercury 2	$0.0031	7.9s	65%	68	68	67	66	65	67%
145	GPT-5 Nano	$0.0042	1.4m	63%	71	67	66	65	64	67%
142	GPT-OSS 120B	$0.0026	54.7s	63%	70	67	66	65	64	67%
147	Nemotron 3 Nano	$0.0007	42.1s	56%	77	69	63	63	61	67%
136	Stealth: Aurora Alpha	$0.0000	14.4s	65%	68	68	67	67	63	66%
144	Inception Mercury	$0.0074	14.4s	62%	69	68	65	63	61	65%
78.22%

Median	Evaluator	Top 3	Flop 3
92.3%	"Not X but Y" pattern overuse	100Arcee AI: Trinity Large (Preview) 100Claude Opus 4.5 100GPT-4o Mini (temp=0)	2GPT-5 Nano 28Mistral Small 4 33Writer: Palmyra X5
49.1%	Adverb-first sentence starts	100LFM2 24B 95Writer: Palmyra X5 95Claude 3.5 Sonnet	0Inception Mercury 0Inception Mercury 2 0GPT-4o Mini (temp=0)
95.8%	Adverbs in dialogue tags	100Grok 4 100Grok 4.3 (Reasoning) 100GPT-5.5	20GPT-4.1 Nano 31GPT-4.1 Mini 38Claude Haiku 4.5
87.5%	AI-ism adverb frequency	98ByteDance Seed 1.6 Flash 98ByteDance Seed 2.0 Lite 98DeepSeek V4 Flash	60Gemma 3 4B 66Claude 3 Haiku 68GPT-4.1 Nano
100.0%	AI-ism character names	100Qwen 3.5 Flash 100DeepSeek V3 (2025-03-24) 100Aion 2.0	80DeepSeek V4 Flash 80DeepSeek V4 Pro 80Mistral NeMO
100.0%	AI-ism location names	100GPT-4o Mini (temp=0) 100Qwen 3.5 9B 100ByteDance Seed 2.0 Mini	96Claude Haiku 4.5
48.8%	AI-ism word frequency	85Claude Opus 4.7 (Reasoning) 85Claude Opus 4.7 84GPT-5.4 Mini (Reasoning)	3Inception Mercury 3GPT-4o Mini (temp=0) 8GPT-4o, Aug. 6th (temp=1)
100.0%	Cliché density	100MiniMax M2.7 100Grok 4.20 (Reasoning) 100Arcee AI: Trinity Mini	20GPT-4o, May 13th (temp=0) 33Mistral Small 3.2 24B 47Claude 3 Haiku
78.8%	Dialogue tag variety (said vs. fancy)	100Claude Opus 4.5 100Claude Sonnet 4.6 (Reasoning) 100Z.AI GLM 5.1	0Qwen 3.5 Plus (2026-02-15) 3Gemma 4 31B 8Gemini 3 Pro (Preview)
17.2%	Em-dash & semicolon overuse	100GPT-5.4 Mini (Reasoning) 100Qwen 3.5 397B A17B 100Qwen3.6 Max Preview	0Gemma 4 31B 0Nemotron 3 Nano 0Grok 4 Fast
100.0%	Emotion telling (show vs. tell)	100Grok 4.20 (Reasoning) 100Gemini 3.1 Flash Lite (Preview) 100Claude Opus 4.7	88Mistral Small 3.2 24B 90GPT-4o Mini (temp=0) 93Hermes 3 70B
93.6%	Filter word density	100Claude 3 Haiku 100Gemma 3 12B 100Mistral Large	8Inception Mercury 2 9Nemotron 3 Nano 11Stealth: Aurora Alpha
100.0%	Gibberish response detection	100Stealth: Healer Alpha 100Mistral NeMO 100Qwen 3.6 Flash	40Llama 3.1 8B 87Rocinante 12B 98Qwen 2.5 72B
100.0%	Markdown formatting overuse	100Claude Opus 4.6 100Cohere Command R+ (Aug. 2024) 100Hermes 3 405B	93ByteDance Seed 1.6 Flash
100.0%	Missing dialogue indicators (quotation marks)	100GPT-5.4 100MiniMax M2.5 100Mistral Medium 3.1	0Qwen3.6 Max Preview 20Qwen 3.5 397B A17B 39Gemini 3.1 Flash Lite (Reasoning)
48.0%	Name drop frequency	94GPT-4.1 Nano 93Claude Opus 4.7 (Reasoning) 90Claude Opus 4.7	0GPT-5.5 (Reasoning) 1Z.AI GLM 4.5 3GPT-5.4 Nano
77.3%	Narrator intent-glossing	100ByteDance Seed 2.0 Lite 100Mistral Small Creative 100GPT-4o, May 13th (temp=0)	11GPT-5 Nano 17Nemotron 3 Nano 20GPT-4o, Aug. 6th (temp=1)
100.0%	Overuse of "that" (subordinate clause padding)	100Claude 3.5 Sonnet 100Mistral Large 2 100Qwen 3.5 Plus (2026-04-20)	64Inception Mercury 74Mistral Small 3.2 24B 74Hermes 3 70B
100.0%	Paragraph length variance	100Mistral Small 4 (Reasoning) 100Gemini 3.1 Pro (Preview) 100GPT-5.4 Mini (Reasoning, Low)	53GPT-5 Nano 65ByteDance Seed 2.0 Lite 67Nemotron 3 Nano
89.8%	Passive voice overuse	100Grok 4.1 Fast 100Llama 3.1 8B 99Hermes 3 405B	65ByteDance Seed 2.0 Mini 70Nemotron 3 Super 76Nemotron 3 Nano
80.0%	Past progressive (was/were + -ing) overuse	100Gemini 2.5 Flash Lite 100DeepSeek-V2 Chat 100GPT-5 Nano	0Gemini 3 Flash (Preview) 10Gemma 4 31B (Reasoning) 12Z.AI GLM 4.6
94.6%	Pronoun-first sentence starts	100Claude Opus 4.5 100GPT-5.4 Mini 100Z.AI GLM 5.1	35Gemma 4 26B 36Gemini 3.1 Flash Lite 37Inception Mercury
97.6%	Purple prose (modifier overload)	100ByteDance Seed 1.6 Flash 100Qwen 3.5 Plus (2026-04-20) 100Qwen 3.5 122B	84GPT-4.1 Nano 86Gemma 3 4B 88ByteDance Seed 2.0 Mini
100.0%	Repeated phrase echo	100GPT-5.5 100Gemma 3 12B 100Qwen 3.6 35B	—
100.0%	Sentence length variance	100Claude Opus 4.5 100Grok 4.3 (Reasoning) 100Claude Opus 4	99Cohere Command R+ (Aug. 2024) 99Hermes 3 70B 100Mistral Small 3.2 24B
56.4%	Sentence opener variety	95Rocinante 12B 91Claude 3.5 Sonnet 91GPT-4o Mini (temp=1)	31Inception Mercury 32Stealth: Aurora Alpha 34GPT-5 Nano
44.5%	Subject-first sentence starts	93GPT-5.4 92Claude Sonnet 4.5 92Grok 4 Fast	0Stealth: Aurora Alpha 1Inception Mercury 2 2Inception Mercury
40.0%	Subordinate conjunction sentence starts	100Gemini 3.1 Flash Lite (Preview) 91Gemini 3.1 Flash Lite 91Qwen 3.6 35B	0DeepSeek V3 (2025-03-24) 0GPT-4.1 Mini 0Inception Mercury
66.0%	Technical jargon density	100GPT-4o, May 13th (temp=0) 100Rocinante 12B 100Qwen 2.5 72B	0Nemotron 3 Nano 0ByteDance Seed 2.0 Lite 0GPT-5 Nano
42.6%	Useless dialogue additions	100Gemini 3.1 Flash Lite (Preview) 100Gemini 3.1 Flash Lite 100GPT-5.5	0GPT-OSS 120B 0DeepSeek V3.1 0Ministral 3 3B

Bad Writing Habits

Mystery: examining a crime scene

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)